@mastra/voice-openai 0.12.0-beta.1 → 0.12.0

package/dist/docs/voice/04-reference.md

@@ -0,0 +1,568 @@
+# Voice API Reference
+
+> API reference for voice - 5 entries
+
+
+---
+
+## Reference: CompositeVoice
+
+> Documentation for the CompositeVoice class, which enables combining multiple voice providers for flexible text-to-speech and speech-to-text operations.
+
+The CompositeVoice class allows you to combine different voice providers for text-to-speech and speech-to-text operations. This is particularly useful when you want to use the best provider for each operation - for example, using OpenAI for speech-to-text and PlayAI for text-to-speech.
+
+CompositeVoice supports both Mastra voice providers and AI SDK model providers
+
+## Constructor Parameters
+
+## Methods
+
+### speak()
+
+Converts text to speech using the configured speaking provider.
+
+Notes:
+
+- If no speaking provider is configured, this method will throw an error
+- Options are passed through to the configured speaking provider
+- Returns a stream of audio data
+
+### listen()
+
+Converts speech to text using the configured listening provider.
+
+Notes:
+
+- If no listening provider is configured, this method will throw an error
+- Options are passed through to the configured listening provider
+- Returns either a string or a stream of transcribed text, depending on the provider
+
+### getSpeakers()
+
+Returns a list of available voices from the speaking provider, where each node contains:
+
+Notes:
+
+- Returns voices from the speaking provider only
+- If no speaking provider is configured, returns an empty array
+- Each voice object will have at least a voiceId property
+- Additional voice properties depend on the speaking provider
+
+## Usage Examples
+
+### Using Mastra Voice Providers
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { OpenAIVoice } from "@mastra/voice-openai";
+import { PlayAIVoice } from "@mastra/voice-playai";
+
+// Create voice providers
+const openai = new OpenAIVoice();
+const playai = new PlayAIVoice();
+
+// Use OpenAI for listening (speech-to-text) and PlayAI for speaking (text-to-speech)
+const voice = new CompositeVoice({
+  input: openai,
+  output: playai,
+});
+
+// Convert speech to text using OpenAI
+const text = await voice.listen(audioStream);
+
+// Convert text to speech using PlayAI
+const audio = await voice.speak("Hello, world!");
+```
+
+### Using AI SDK Model Providers
+
+You can pass AI SDK transcription and speech models directly to CompositeVoice:
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { openai } from "@ai-sdk/openai";
+import { elevenlabs } from "@ai-sdk/elevenlabs";
+
+// Use AI SDK models directly - they will be auto-wrapped
+const voice = new CompositeVoice({
+  input: openai.transcription('whisper-1'),      // AI SDK transcription
+  output: elevenlabs.speech('eleven_turbo_v2'),  // AI SDK speech
+});
+
+// Works the same way as with Mastra providers
+const text = await voice.listen(audioStream);
+const audio = await voice.speak("Hello from AI SDK!");
+```
+
+### Mix and Match
+
+You can combine Mastra providers with AI SDK models:
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { PlayAIVoice } from "@mastra/voice-playai";
+import { groq } from "@ai-sdk/groq";
+
+const voice = new CompositeVoice({
+  input: groq.transcription('whisper-large-v3'),  // AI SDK for STT
+  output: new PlayAIVoice(),                       // Mastra for TTS
+});
+```
+
+---
+
+## Reference: OpenAI
+
+> Documentation for the OpenAIVoice class, providing text-to-speech and speech-to-text capabilities.
+
+The OpenAIVoice class in Mastra provides text-to-speech and speech-to-text capabilities using OpenAI's models.
+
+## Usage Example
+
+```typescript
+import { OpenAIVoice } from "@mastra/voice-openai";
+
+// Initialize with default configuration using environment variables
+const voice = new OpenAIVoice();
+
+// Or initialize with specific configuration
+const voiceWithConfig = new OpenAIVoice({
+  speechModel: {
+    name: "tts-1-hd",
+    apiKey: "your-openai-api-key",
+  },
+  listeningModel: {
+    name: "whisper-1",
+    apiKey: "your-openai-api-key",
+  },
+  speaker: "alloy", // Default voice
+});
+
+// Convert text to speech
+const audioStream = await voice.speak("Hello, how can I help you?", {
+  speaker: "nova", // Override default voice
+  speed: 1.2, // Adjust speech speed
+});
+
+// Convert speech to text
+const text = await voice.listen(audioStream, {
+  filetype: "mp3",
+});
+```
+
+## Configuration
+
+### Constructor Options
+
+### OpenAIConfig
+
+## Methods
+
+### speak()
+
+Converts text to speech using OpenAI's text-to-speech models.
+
+Returns: `Promise<NodeJS.ReadableStream>`
+
+### listen()
+
+Transcribes audio using OpenAI's Whisper model.
+
+Returns: `Promise<string>`
+
+### getSpeakers()
+
+Returns an array of available voice options, where each node contains:
+
+## Notes
+
+- API keys can be provided via constructor options or the `OPENAI_API_KEY` environment variable
+- The `tts-1-hd` model provides higher quality audio but may have slower processing times
+- Speech recognition supports multiple audio formats including mp3, wav, and webm
+
+---
+
+## Reference: voice.getSpeakers()
+
+> Documentation for the getSpeakers() method available in voice providers, which retrieves available voice options.
+
+The `getSpeakers()` method retrieves a list of available voice options (speakers) from the voice provider. This allows applications to present users with voice choices or programmatically select the most appropriate voice for different contexts.
+
+## Usage Example
+
+```typescript
+import { OpenAIVoice } from "@mastra/voice-openai";
+import { ElevenLabsVoice } from "@mastra/voice-elevenlabs";
+
+// Initialize voice providers
+const openaiVoice = new OpenAIVoice();
+const elevenLabsVoice = new ElevenLabsVoice({
+  apiKey: process.env.ELEVENLABS_API_KEY,
+});
+
+// Get available speakers from OpenAI
+const openaiSpeakers = await openaiVoice.getSpeakers();
+console.log("OpenAI voices:", openaiSpeakers);
+// Example output: [{ voiceId: "alloy" }, { voiceId: "echo" }, { voiceId: "fable" }, ...]
+
+// Get available speakers from ElevenLabs
+const elevenLabsSpeakers = await elevenLabsVoice.getSpeakers();
+console.log("ElevenLabs voices:", elevenLabsSpeakers);
+// Example output: [{ voiceId: "21m00Tcm4TlvDq8ikWAM", name: "Rachel" }, ...]
+
+// Use a specific voice for speech
+const text = "Hello, this is a test of different voices.";
+await openaiVoice.speak(text, { speaker: openaiSpeakers[2].voiceId });
+await elevenLabsVoice.speak(text, { speaker: elevenLabsSpeakers[0].voiceId });
+```
+
+## Parameters
+
+This method does not accept any parameters.
+
+## Return Value
+
+## Provider-Specific Metadata
+
+Different voice providers return different metadata for their voices:
+
+  **OpenAI:**
+
+    
+  
+
+**OpenAI Realtime:**
+
+  
+
+**Deepgram:**
+
+  
+
+**ElevenLabs:**
+
+  
+
+**Google:**
+
+  
+
+**Azure:**
+
+  
+
+**Murf:**
+
+  
+
+**PlayAI:**
+
+  
+
+**Speechify:**
+
+  
+
+**Sarvam:**
+
+    
+  
+
+## Notes
+
+- The available voices vary significantly between providers
+- Some providers may require authentication to retrieve the full list of voices
+- The default implementation returns an empty array if the provider doesn't support this method
+- For performance reasons, consider caching the results if you need to display the list frequently
+- The `voiceId` property is guaranteed to be present for all providers, but additional metadata varies
+
+---
+
+## Reference: voice.listen()
+
+> Documentation for the listen() method available in all Mastra voice providers, which converts speech to text.
+
+The `listen()` method is a core function available in all Mastra voice providers that converts speech to text. It takes an audio stream as input and returns the transcribed text.
+
+## Parameters
+
+## Return Value
+
+Returns one of the following:
+
+- `Promise<string>`: A promise that resolves to the transcribed text
+- `Promise<NodeJS.ReadableStream>`: A promise that resolves to a stream of transcribed text (for streaming transcription)
+- `Promise<void>`: For real-time providers that emit 'writing' events instead of returning text directly
+
+## Provider-Specific Options
+
+Each voice provider may support additional options specific to their implementation. Here are some examples:
+
+### OpenAI
+
+### Google
+
+### Deepgram
+
+## Usage Example
+
+```typescript
+import { OpenAIVoice } from "@mastra/voice-openai";
+import { getMicrophoneStream } from "@mastra/node-audio";
+import { createReadStream } from "fs";
+import path from "path";
+
+// Initialize a voice provider
+const voice = new OpenAIVoice({
+  listeningModel: {
+    name: "whisper-1",
+    apiKey: process.env.OPENAI_API_KEY,
+  },
+});
+
+// Basic usage with a file stream
+const audioFilePath = path.join(process.cwd(), "audio.mp3");
+const audioStream = createReadStream(audioFilePath);
+const transcript = await voice.listen(audioStream, {
+  filetype: "mp3",
+});
+console.log("Transcribed text:", transcript);
+
+// Using a microphone stream
+const microphoneStream = getMicrophoneStream(); // Assume this function gets audio input
+const transcription = await voice.listen(microphoneStream);
+
+// With provider-specific options
+const transcriptWithOptions = await voice.listen(audioStream, {
+  language: "en",
+  prompt: "This is a conversation about artificial intelligence.",
+});
+```
+
+## Using with CompositeVoice
+
+When using `CompositeVoice`, the `listen()` method delegates to the configured listening provider:
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { OpenAIVoice } from "@mastra/voice-openai";
+import { PlayAIVoice } from "@mastra/voice-playai";
+
+const voice = new CompositeVoice({
+  input: new OpenAIVoice(),
+  output: new PlayAIVoice(),
+});
+
+// This will use the OpenAIVoice provider
+const transcript = await voice.listen(audioStream);
+```
+
+### Using AI SDK Model Providers
+
+You can also use AI SDK transcription models directly with `CompositeVoice`:
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { openai } from "@ai-sdk/openai";
+import { groq } from "@ai-sdk/groq";
+
+// Use AI SDK transcription models
+const voice = new CompositeVoice({
+  input: openai.transcription('whisper-1'),  // AI SDK model
+  output: new PlayAIVoice(),                 // Mastra provider
+});
+
+// Works the same way
+const transcript = await voice.listen(audioStream);
+
+// Provider-specific options can be passed through
+const transcriptWithOptions = await voice.listen(audioStream, {
+  providerOptions: {
+    openai: {
+      language: 'en',
+      prompt: 'This is about AI',
+    }
+  }
+});
+```
+
+See the [CompositeVoice reference](https://mastra.ai/reference/v1/voice/composite-voice) for more details on AI SDK integration.
+
+## Realtime Voice Providers
+
+When using realtime voice providers like `OpenAIRealtimeVoice`, the `listen()` method behaves differently:
+
+- Instead of returning transcribed text, it emits 'writing' events with the transcribed text
+- You need to register an event listener to receive the transcription
+
+```typescript
+import { OpenAIRealtimeVoice } from "@mastra/voice-openai-realtime";
+import { getMicrophoneStream } from "@mastra/node-audio";
+
+const voice = new OpenAIRealtimeVoice();
+await voice.connect();
+
+// Register event listener for transcription
+voice.on("writing", ({ text, role }) => {
+  console.log(`${role}: ${text}`);
+});
+
+// This will emit 'writing' events instead of returning text
+const microphoneStream = getMicrophoneStream();
+await voice.listen(microphoneStream);
+```
+
+## Notes
+
+- Not all voice providers support speech-to-text functionality (e.g., PlayAI, Speechify)
+- The behavior of `listen()` may vary slightly between providers, but all implementations follow the same basic interface
+- When using a realtime voice provider, the method might not return text directly but instead emit a 'writing' event
+- The audio format supported depends on the provider. Common formats include MP3, WAV, and M4A
+- Some providers support streaming transcription, where text is returned as it's transcribed
+- For best performance, consider closing or ending the audio stream when you're done with it
+
+## Related Methods
+
+- [voice.speak()](./voice.speak) - Converts text to speech
+- [voice.send()](./voice.send) - Sends audio data to the voice provider in real-time
+- [voice.on()](./voice.on) - Registers an event listener for voice events
+
+---
+
+## Reference: voice.speak()
+
+> Documentation for the speak() method available in all Mastra voice providers, which converts text to speech.
+
+The `speak()` method is a core function available in all Mastra voice providers that converts text to speech. It takes text input and returns an audio stream that can be played or saved.
+
+## Parameters
+
+## Return Value
+
+Returns a `Promise<NodeJS.ReadableStream | void>` where:
+
+- `NodeJS.ReadableStream`: A stream of audio data that can be played or saved
+- `void`: When using a realtime voice provider that emits audio through events instead of returning it directly
+
+## Provider-Specific Options
+
+Each voice provider may support additional options specific to their implementation. Here are some examples:
+
+### OpenAI
+
+### ElevenLabs
+
+### Google
+
+### Murf
+
+## Usage Example
+
+```typescript
+import { OpenAIVoice } from "@mastra/voice-openai";
+// Initialize a voice provider
+const voice = new OpenAIVoice({
+  speaker: "alloy", // Default voice
+});
+// Basic usage with default settings
+const audioStream = await voice.speak("Hello, world!");
+// Using a different voice for this specific request
+const audioStreamWithDifferentVoice = await voice.speak("Hello again!", {
+  speaker: "nova",
+});
+// Using provider-specific options
+const audioStreamWithOptions = await voice.speak("Hello with options!", {
+  speaker: "echo",
+  speed: 1.2, // OpenAI-specific option
+});
+// Using a text stream as input
+import { Readable } from "stream";
+const textStream = Readable.from(["Hello", " from", " a", " stream!"]);
+const audioStreamFromTextStream = await voice.speak(textStream);
+```
+
+## Using with CompositeVoice
+
+When using `CompositeVoice`, the `speak()` method delegates to the configured speaking provider:
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { OpenAIVoice } from "@mastra/voice-openai";
+import { PlayAIVoice } from "@mastra/voice-playai";
+
+const voice = new CompositeVoice({
+  output: new PlayAIVoice(),
+  input: new OpenAIVoice(),
+});
+
+// This will use the PlayAIVoice provider
+const audioStream = await voice.speak("Hello, world!");
+```
+
+### Using AI SDK Model Providers
+
+You can also use AI SDK speech models directly with `CompositeVoice`:
+
+```typescript
+import { CompositeVoice } from "@mastra/core/voice";
+import { openai } from "@ai-sdk/openai";
+import { elevenlabs } from "@ai-sdk/elevenlabs";
+
+// Use AI SDK speech models
+const voice = new CompositeVoice({
+  output: elevenlabs.speech('eleven_turbo_v2'),  // AI SDK model
+  input: openai.transcription('whisper-1'),      // AI SDK model
+});
+
+// Works the same way
+const audioStream = await voice.speak("Hello from AI SDK!");
+
+// Provider-specific options can be passed through
+const audioWithOptions = await voice.speak("Hello with options!", {
+  speaker: 'Rachel',  // ElevenLabs voice
+  providerOptions: {
+    elevenlabs: {
+      stability: 0.5,
+      similarity_boost: 0.75,
+    }
+  }
+});
+```
+
+See the [CompositeVoice reference](https://mastra.ai/reference/v1/voice/composite-voice) for more details on AI SDK integration.
+
+## Realtime Voice Providers
+
+When using realtime voice providers like `OpenAIRealtimeVoice`, the `speak()` method behaves differently:
+
+- Instead of returning an audio stream, it emits a 'speaking' event with the audio data
+- You need to register an event listener to receive the audio chunks
+
+```typescript
+import { OpenAIRealtimeVoice } from "@mastra/voice-openai-realtime";
+import Speaker from "@mastra/node-speaker";
+
+const speaker = new Speaker({
+  sampleRate: 24100, // Audio sample rate in Hz - standard for high-quality audio on MacBook Pro
+  channels: 1, // Mono audio output (as opposed to stereo which would be 2)
+  bitDepth: 16, // Bit depth for audio quality - CD quality standard (16-bit resolution)
+});
+
+const voice = new OpenAIRealtimeVoice();
+await voice.connect();
+// Register event listener for audio chunks
+voice.on("speaker", (stream) => {
+  // Handle audio chunk (e.g., play it or save it)
+  stream.pipe(speaker);
+});
+// This will emit 'speaking' events instead of returning a stream
+await voice.speak("Hello, this is realtime speech!");
+```
+
+## Notes
+
+- The behavior of `speak()` may vary slightly between providers, but all implementations follow the same basic interface.
+- When using a realtime voice provider, the method might not return an audio stream directly but instead emit a 'speaking' event.
+- If a text stream is provided as input, the provider will typically convert it to a string before processing.
+- The audio format of the returned stream depends on the provider. Common formats include MP3, WAV, and OGG.
+- For best performance, consider closing or ending the audio stream when you're done with it.

package/dist/index.cjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/index.ts"],"names":["MastraVoice","OpenAI","PassThrough"],"mappings":";;;;;;;;;;;AA6BO,IAAM,WAAA,GAAN,cAA0BA,iBAAA,CAAY;AAAA,EAC3C,YAAA;AAAA,EACA,eAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAWA,WAAA,CAAY;AAAA,IACV,cAAA;AAAA,IACA,WAAA;AAAA,IACA;AAAA,GACF,GAII,EAAC,EAAG;AACN,IAAA,MAAM,aAAA,GAAgB,QAAQ,GAAA,CAAI,cAAA;AAClC,IAAA,MAAM,kBAAA,GAAqB;AAAA,MACzB,IAAA,EAAM,OAAA;AAAA,MACN,MAAA,EAAQ;AAAA,KACV;AACA,IAAA,MAAM,qBAAA,GAAwB;AAAA,MAC5B,IAAA,EAAM,WAAA;AAAA,MACN,MAAA,EAAQ;AAAA,KACV;AAEA,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,WAAA,EAAa,IAAA,IAAQ,kBAAA,CAAmB,IAAA;AAAA,QAC9C,MAAA,EAAQ,WAAA,EAAa,MAAA,IAAU,kBAAA,CAAmB;AAAA,OACpD;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,cAAA,EAAgB,IAAA,IAAQ,qBAAA,CAAsB,IAAA;AAAA,QACpD,MAAA,EAAQ,cAAA,EAAgB,MAAA,IAAU,qBAAA,CAAsB;AAAA,OAC1D;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,YAAA,GAAe,aAAa,MAAA,IAAU,aAAA;AAC5C,IAAA,IAAI,CAAC,YAAA,EAAc;AACjB,MAAA,MAAM,IAAI,MAAM,sCAAsC,CAAA;AAAA,IACxD;AACA,IAAA,IAAA,CAAK,YAAA,GAAe,IAAIC,uBAAA,CAAO;AAAA,MAC7B,MAAA,EAAQ,YAAA;AAAA,MACR,GAAG,WAAA,EAAa;AAAA,KACjB,CAAA;AAED,IAAA,MAAM,eAAA,GAAkB,gBAAgB,MAAA,IAAU,aAAA;AAClD,IAAA,IAAI,CAAC,eAAA,EAAiB;AACpB,MAAA,MAAM,IAAI,MAAM,yCAAyC,CAAA;AAAA,IAC3D;AACA,IAAA,IAAA,CAAK,eAAA,GAAkB,IAAIA,uBAAA,CAAO;AAAA,MAChC,MAAA,EAAQ,eAAA;AAAA,MACR,GAAG,cAAA,EAAgB;AAAA,KACpB,CAAA;AAED,IAAA,IAAI,CAAC,IAAA,CAAK,YAAA,IAAgB,CAAC,KAAK,eAAA,EAAiB;AAC/C,MAAA,MAAM,IAAI,MAAM,0FAA0F,CAAA;AAAA,IAC5G;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,WAAA,GAA0D;AAC9D,IAAA,IAAI,CAAC,KAAK,WAAA,EAAa;AACrB,MAAA,MAAM,IAAI,MAAM,6BAA6B,CAAA;AAAA,IAC/C;AAEA,IAAA,OAAO;AAAA,MACL,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,SAAA,EAAU;AAAA,MACrB,EAAE,SAAS,KAAA,EAAM;AAAA,MACjB,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA;AAAO,KACpB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,KAAA,CACJ,KAAA,EACA,OAAA,EAKgC;AAChC,IAAA,IAAI,CAAC,KAAK,YAAA,EAAc;AACtB,MAAA,MAAM,IAAI,MAAM,6BAA6B,CAAA;AAAA,IAC/C;AAEA,IAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,MAAA,MAAM,SAAmB,EAAC;AAC1B,MAAA,WAAA,MAAiB,SAAS,KAAA,EAAO;AAC/B,QAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,UAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,QAChC,CAAA,MAAO;AACL,UAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,QACnB;AAAA,MACF;AACA,MAAA,KAAA,GAAQ,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA,CAAE,SAAS,OAAO,CAAA;AAAA,IAChD;AAEA,IAAA,IAAI,KAAA,CAAM,IAAA,EAAK,CAAE,MAAA,KAAW,CAAA,EAAG;AAC7B,MAAA,MAAM,IAAI,MAAM,qBAAqB,CAAA;AAAA,IACvC;AAEA,IAAA,MAAM,EAAE,SAAS,cAAA,EAAgB,KAAA,EAAO,GAAG,YAAA,EAAa,GAAI,WAAW,EAAC;AAExE,IAAA,MAAM,WAAW,MAAM,IAAA,CAAK,YAAA,CAAc,KAAA,CAAM,OAAO,MAAA,CAAO;AAAA,MAC5D,KAAA,EAAO,IAAA,CAAK,WAAA,EAAa,IAAA,IAAQ,OAAA;AAAA,MACjC,KAAA,EAAQ,WAAW,IAAA,CAAK,OAAA;AAAA,MACxB,iBAAiB,cAAA,IAAkB,KAAA;AAAA,MACnC,KAAA;AAAA,MACA,OAAO,KAAA,IAAS,CAAA;AAAA,MAChB,GAAG;AAAA,KACJ,CAAA;AAED,IAAA,MAAM,WAAA,GAAc,IAAIC,kBAAA,EAAY;AACpC,IAAA,MAAM,SAAS,MAAA,CAAO,IAAA,CAAK,MAAM,QAAA,CAAS,aAAa,CAAA;AACvD,IAAA,WAAA,CAAY,IAAI,MAAM,CAAA;AACtB,IAAA,OAAO,WAAA;AAAA,EACT;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAM,WAAA,GAAc;AAClB,IAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AACzB,MAAA,OAAO,EAAE,SAAS,KAAA,EAAM;AAAA,IAC1B;AACA,IAAA,OAAO,EAAE,SAAS,IAAA,EAAK;AAAA,EACzB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,MAAA,CACJ,WAAA,EACA,OAAA,EAIiB;AACjB,IAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AACzB,MAAA,MAAM,IAAI,MAAM,gCAAgC,CAAA;AAAA,IAClD;AAEA,IAAA,MAAM,SAAmB,EAAC;AAC1B,IAAA,WAAA,MAAiB,SAAS,WAAA,EAAa;AACrC,MAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,QAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,MAChC,CAAA,MAAO;AACL,QAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,MACnB;AAAA,IACF;AACA,IAAA,MAAM,WAAA,GAAc,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA;AAExC,IAAA,MAAM,EAAE,QAAA,EAAU,GAAG,YAAA,EAAa,GAAI,WAAW,EAAC;AAClD,IAAA,MAAM,IAAA,GAAO,IAAI,IAAA,CAAK,CAAC,WAAW,CAAA,EAAG,CAAA,MAAA,EAAS,QAAA,IAAY,KAAK,CAAA,CAAE,CAAA;AAEjE,IAAA,MAAM,WAAW,MAAM,IAAA,CAAK,eAAA,CAAiB,KAAA,CAAM,eAAe,MAAA,CAAO;AAAA,MACvE,KAAA,EAAO,IAAA,CAAK,cAAA,EAAgB,IAAA,IAAQ,WAAA;AAAA,MACpC,IAAA;AAAA,MACA,GAAG;AAAA,KACJ,CAAA;AAED,IAAA,OAAO,QAAA,CAAS,IAAA;AAAA,EAClB;AACF","file":"index.cjs","sourcesContent":["import { PassThrough } from 'stream';\n\nimport { MastraVoice } from '@mastra/core/voice';\nimport OpenAI from 'openai';\nimport type { ClientOptions } from 'openai';\n\ntype OpenAIVoiceId = 'alloy' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer' | 'ash' | 'coral' | 'sage';\ntype OpenAIModel = 'tts-1' | 'tts-1-hd' | 'whisper-1';\n\nexport interface OpenAIConfig {\n  name?: OpenAIModel;\n  apiKey?: string;\n  options?: Omit<ClientOptions, 'apiKey'>;\n}\n\nexport interface OpenAIVoiceConfig {\n  speech?: {\n    model: 'tts-1' | 'tts-1-hd';\n    apiKey?: string;\n    speaker?: OpenAIVoiceId;\n    options?: Omit<ClientOptions, 'apiKey'>;\n  };\n  listening?: {\n    model: 'whisper-1';\n    apiKey?: string;\n    options?: Omit<ClientOptions, 'apiKey'>;\n  };\n}\n\nexport class OpenAIVoice extends MastraVoice {\n  speechClient?: OpenAI;\n  listeningClient?: OpenAI;\n\n  /**\n   * Constructs an instance of OpenAIVoice with optional configurations for speech and listening models.\n   *\n   * @param {Object} [config] - Configuration options for the OpenAIVoice instance.\n   * @param {OpenAIConfig} [config.listeningModel] - Configuration for the listening model, including model name and API key.\n   * @param {OpenAIConfig} [config.speechModel] - Configuration for the speech model, including model name and API key.\n   * @param {string} [config.speaker] - The default speaker's voice to use for speech synthesis.\n   * @throws {Error} - Throws an error if no API key is provided for either the speech or listening model.\n   */\n  constructor({\n    listeningModel,\n    speechModel,\n    speaker,\n  }: {\n    listeningModel?: OpenAIConfig;\n    speechModel?: OpenAIConfig;\n    speaker?: string;\n  } = {}) {\n    const defaultApiKey = process.env.OPENAI_API_KEY;\n    const defaultSpeechModel = {\n      name: 'tts-1',\n      apiKey: defaultApiKey,\n    };\n    const defaultListeningModel = {\n      name: 'whisper-1',\n      apiKey: defaultApiKey,\n    };\n\n    super({\n      speechModel: {\n        name: speechModel?.name ?? defaultSpeechModel.name,\n        apiKey: speechModel?.apiKey ?? defaultSpeechModel.apiKey,\n      },\n      listeningModel: {\n        name: listeningModel?.name ?? defaultListeningModel.name,\n        apiKey: listeningModel?.apiKey ?? defaultListeningModel.apiKey,\n      },\n      speaker: speaker ?? 'alloy',\n    });\n\n    const speechApiKey = speechModel?.apiKey || defaultApiKey;\n    if (!speechApiKey) {\n      throw new Error('No API key provided for speech model');\n    }\n    this.speechClient = new OpenAI({\n      apiKey: speechApiKey,\n      ...speechModel?.options,\n    });\n\n    const listeningApiKey = listeningModel?.apiKey || defaultApiKey;\n    if (!listeningApiKey) {\n      throw new Error('No API key provided for listening model');\n    }\n    this.listeningClient = new OpenAI({\n      apiKey: listeningApiKey,\n      ...listeningModel?.options,\n    });\n\n    if (!this.speechClient && !this.listeningClient) {\n      throw new Error('At least one of OPENAI_API_KEY, speechModel.apiKey, or listeningModel.apiKey must be set');\n    }\n  }\n\n  /**\n   * Retrieves a list of available speakers for the speech model.\n   *\n   * @returns {Promise<Array<{ voiceId: OpenAIVoiceId }>>} - A promise that resolves to an array of objects,\n   * each containing a `voiceId` representing an available speaker.\n   * @throws {Error} - Throws an error if the speech model is not configured.\n   */\n  async getSpeakers(): Promise<Array<{ voiceId: OpenAIVoiceId }>> {\n    if (!this.speechModel) {\n      throw new Error('Speech model not configured');\n    }\n\n    return [\n      { voiceId: 'alloy' },\n      { voiceId: 'echo' },\n      { voiceId: 'fable' },\n      { voiceId: 'onyx' },\n      { voiceId: 'nova' },\n      { voiceId: 'shimmer' },\n      { voiceId: 'ash' },\n      { voiceId: 'coral' },\n      { voiceId: 'sage' },\n    ];\n  }\n\n  /**\n   * Converts text or audio input into speech using the configured speech model.\n   *\n   * @param {string | NodeJS.ReadableStream} input - The text or audio stream to be converted into speech.\n   * @param {Object} [options] - Optional parameters for the speech synthesis.\n   * @param {string} [options.speaker] - The speaker's voice to use for the speech synthesis.\n   * @param {number} [options.speed] - The speed at which the speech should be synthesized.\n   * @returns {Promise<NodeJS.ReadableStream>} - A promise that resolves to a readable stream of the synthesized audio.\n   * @throws {Error} - Throws an error if the speech model is not configured or if the input text is empty.\n   */\n  async speak(\n    input: string | NodeJS.ReadableStream,\n    options?: {\n      speaker?: string;\n      speed?: number;\n      [key: string]: any;\n    },\n  ): Promise<NodeJS.ReadableStream> {\n    if (!this.speechClient) {\n      throw new Error('Speech model not configured');\n    }\n\n    if (typeof input !== 'string') {\n      const chunks: Buffer[] = [];\n      for await (const chunk of input) {\n        if (typeof chunk === 'string') {\n          chunks.push(Buffer.from(chunk));\n        } else {\n          chunks.push(chunk);\n        }\n      }\n      input = Buffer.concat(chunks).toString('utf-8');\n    }\n\n    if (input.trim().length === 0) {\n      throw new Error('Input text is empty');\n    }\n\n    const { speaker, responseFormat, speed, ...otherOptions } = options || {};\n\n    const response = await this.speechClient!.audio.speech.create({\n      model: this.speechModel?.name ?? 'tts-1',\n      voice: (speaker ?? this.speaker) as OpenAIVoiceId,\n      response_format: responseFormat ?? 'mp3',\n      input,\n      speed: speed || 1.0,\n      ...otherOptions,\n    });\n\n    const passThrough = new PassThrough();\n    const buffer = Buffer.from(await response.arrayBuffer());\n    passThrough.end(buffer);\n    return passThrough;\n  }\n\n  /**\n   * Checks if listening capabilities are enabled.\n   *\n   * @returns {Promise<{ enabled: boolean }>}\n   */\n  async getListener() {\n    if (!this.listeningClient) {\n      return { enabled: false };\n    }\n    return { enabled: true };\n  }\n\n  /**\n   * Transcribes audio from a given stream using the configured listening model.\n   *\n   * @param {NodeJS.ReadableStream} audioStream - The audio stream to be transcribed.\n   * @param {Object} [options] - Optional parameters for the transcription.\n   * @param {string} [options.filetype] - The file type of the audio stream.\n   *                                      Supported types include 'mp3', 'mp4', 'mpeg', 'mpga', 'm4a', 'wav', 'webm'.\n   * @returns {Promise<string>} - A promise that resolves to the transcribed text.\n   * @throws {Error} - Throws an error if the listening model is not configured.\n   */\n  async listen(\n    audioStream: NodeJS.ReadableStream,\n    options?: {\n      filetype?: 'mp3' | 'mp4' | 'mpeg' | 'mpga' | 'm4a' | 'wav' | 'webm';\n      [key: string]: any;\n    },\n  ): Promise<string> {\n    if (!this.listeningClient) {\n      throw new Error('Listening model not configured');\n    }\n\n    const chunks: Buffer[] = [];\n    for await (const chunk of audioStream) {\n      if (typeof chunk === 'string') {\n        chunks.push(Buffer.from(chunk));\n      } else {\n        chunks.push(chunk);\n      }\n    }\n    const audioBuffer = Buffer.concat(chunks);\n\n    const { filetype, ...otherOptions } = options || {};\n    const file = new File([audioBuffer], `audio.${filetype || 'mp3'}`);\n\n    const response = await this.listeningClient!.audio.transcriptions.create({\n      model: this.listeningModel?.name || 'whisper-1',\n      file: file as any,\n      ...otherOptions,\n    });\n\n    return response.text;\n  }\n}\n"]}
+{"version":3,"sources":["../src/index.ts"],"names":["MastraVoice","OpenAI","PassThrough"],"mappings":";;;;;;;;;;;AA6BO,IAAM,WAAA,GAAN,cAA0BA,iBAAA,CAAY;AAAA,EAC3C,YAAA;AAAA,EACA,eAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAWA,WAAA,CAAY;AAAA,IACV,cAAA;AAAA,IACA,WAAA;AAAA,IACA;AAAA,GACF,GAII,EAAC,EAAG;AACN,IAAA,MAAM,aAAA,GAAgB,QAAQ,GAAA,CAAI,cAAA;AAClC,IAAA,MAAM,kBAAA,GAAqB;AAAA,MACzB,IAAA,EAAM,OAAA;AAAA,MACN,MAAA,EAAQ;AAAA,KACV;AACA,IAAA,MAAM,qBAAA,GAAwB;AAAA,MAC5B,IAAA,EAAM,WAAA;AAAA,MACN,MAAA,EAAQ;AAAA,KACV;AAEA,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,WAAA,EAAa,IAAA,IAAQ,kBAAA,CAAmB,IAAA;AAAA,QAC9C,MAAA,EAAQ,WAAA,EAAa,MAAA,IAAU,kBAAA,CAAmB;AAAA,OACpD;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,cAAA,EAAgB,IAAA,IAAQ,qBAAA,CAAsB,IAAA;AAAA,QACpD,MAAA,EAAQ,cAAA,EAAgB,MAAA,IAAU,qBAAA,CAAsB;AAAA,OAC1D;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,YAAA,GAAe,aAAa,MAAA,IAAU,aAAA;AAC5C,IAAA,IAAI,CAAC,YAAA,EAAc;AACjB,MAAA,MAAM,IAAI,MAAM,sCAAsC,CAAA;AAAA,IACxD;AACA,IAAA,IAAA,CAAK,YAAA,GAAe,IAAIC,uBAAA,CAAO;AAAA,MAC7B,MAAA,EAAQ,YAAA;AAAA,MACR,GAAG,WAAA,EAAa;AAAA,KACjB,CAAA;AAED,IAAA,MAAM,eAAA,GAAkB,gBAAgB,MAAA,IAAU,aAAA;AAClD,IAAA,IAAI,CAAC,eAAA,EAAiB;AACpB,MAAA,MAAM,IAAI,MAAM,yCAAyC,CAAA;AAAA,IAC3D;AACA,IAAA,IAAA,CAAK,eAAA,GAAkB,IAAIA,uBAAA,CAAO;AAAA,MAChC,MAAA,EAAQ,eAAA;AAAA,MACR,GAAG,cAAA,EAAgB;AAAA,KACpB,CAAA;AAED,IAAA,IAAI,CAAC,IAAA,CAAK,YAAA,IAAgB,CAAC,KAAK,eAAA,EAAiB;AAC/C,MAAA,MAAM,IAAI,MAAM,0FAA0F,CAAA;AAAA,IAC5G;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,WAAA,GAA0D;AAC9D,IAAA,IAAI,CAAC,KAAK,WAAA,EAAa;AACrB,MAAA,MAAM,IAAI,MAAM,6BAA6B,CAAA;AAAA,IAC/C;AAEA,IAAA,OAAO;AAAA,MACL,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,SAAA,EAAU;AAAA,MACrB,EAAE,SAAS,KAAA,EAAM;AAAA,MACjB,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA;AAAO,KACpB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,KAAA,CACJ,KAAA,EACA,OAAA,EAKgC;AAChC,IAAA,IAAI,CAAC,KAAK,YAAA,EAAc;AACtB,MAAA,MAAM,IAAI,MAAM,6BAA6B,CAAA;AAAA,IAC/C;AAEA,IAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,MAAA,MAAM,SAAmB,EAAC;AAC1B,MAAA,WAAA,MAAiB,SAAS,KAAA,EAAO;AAC/B,QAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,UAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,QAChC,CAAA,MAAO;AACL,UAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,QACnB;AAAA,MACF;AACA,MAAA,KAAA,GAAQ,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA,CAAE,SAAS,OAAO,CAAA;AAAA,IAChD;AAEA,IAAA,IAAI,KAAA,CAAM,IAAA,EAAK,CAAE,MAAA,KAAW,CAAA,EAAG;AAC7B,MAAA,MAAM,IAAI,MAAM,qBAAqB,CAAA;AAAA,IACvC;AAEA,IAAA,MAAM,EAAE,SAAS,cAAA,EAAgB,KAAA,EAAO,GAAG,YAAA,EAAa,GAAI,WAAW,EAAC;AAExE,IAAA,MAAM,WAAW,MAAM,IAAA,CAAK,YAAA,CAAc,KAAA,CAAM,OAAO,MAAA,CAAO;AAAA,MAC5D,KAAA,EAAO,IAAA,CAAK,WAAA,EAAa,IAAA,IAAQ,OAAA;AAAA,MACjC,KAAA,EAAQ,WAAW,IAAA,CAAK,OAAA;AAAA,MACxB,iBAAiB,cAAA,IAAkB,KAAA;AAAA,MACnC,KAAA;AAAA,MACA,OAAO,KAAA,IAAS,CAAA;AAAA,MAChB,GAAG;AAAA,KACJ,CAAA;AAED,IAAA,MAAM,WAAA,GAAc,IAAIC,kBAAA,EAAY;AACpC,IAAA,MAAM,SAAS,MAAA,CAAO,IAAA,CAAK,MAAM,QAAA,CAAS,aAAa,CAAA;AACvD,IAAA,WAAA,CAAY,IAAI,MAAM,CAAA;AACtB,IAAA,OAAO,WAAA;AAAA,EACT;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAM,WAAA,GAAc;AAClB,IAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AACzB,MAAA,OAAO,EAAE,SAAS,KAAA,EAAM;AAAA,IAC1B;AACA,IAAA,OAAO,EAAE,SAAS,IAAA,EAAK;AAAA,EACzB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,MAAA,CACJ,WAAA,EACA,OAAA,EAIiB;AACjB,IAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AACzB,MAAA,MAAM,IAAI,MAAM,gCAAgC,CAAA;AAAA,IAClD;AAEA,IAAA,MAAM,SAAmB,EAAC;AAC1B,IAAA,WAAA,MAAiB,SAAS,WAAA,EAAa;AACrC,MAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,QAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,MAChC,CAAA,MAAO;AACL,QAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,MACnB;AAAA,IACF;AACA,IAAA,MAAM,WAAA,GAAc,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA;AAExC,IAAA,MAAM,EAAE,QAAA,EAAU,GAAG,YAAA,EAAa,GAAI,WAAW,EAAC;AAClD,IAAA,MAAM,IAAA,GAAO,IAAI,IAAA,CAAK,CAAC,WAAW,CAAA,EAAG,CAAA,MAAA,EAAS,QAAA,IAAY,KAAK,CAAA,CAAE,CAAA;AAEjE,IAAA,MAAM,WAAW,MAAM,IAAA,CAAK,eAAA,CAAiB,KAAA,CAAM,eAAe,MAAA,CAAO;AAAA,MACvE,KAAA,EAAO,IAAA,CAAK,cAAA,EAAgB,IAAA,IAAQ,WAAA;AAAA,MACpC,IAAA;AAAA,MACA,GAAG;AAAA,KACJ,CAAA;AAED,IAAA,OAAO,QAAA,CAAS,IAAA;AAAA,EAClB;AACF","file":"index.cjs","sourcesContent":["import { PassThrough } from 'node:stream';\n\nimport { MastraVoice } from '@mastra/core/voice';\nimport OpenAI from 'openai';\nimport type { ClientOptions } from 'openai';\n\ntype OpenAIVoiceId = 'alloy' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer' | 'ash' | 'coral' | 'sage';\ntype OpenAIModel = 'tts-1' | 'tts-1-hd' | 'whisper-1';\n\nexport interface OpenAIConfig {\n  name?: OpenAIModel;\n  apiKey?: string;\n  options?: Omit<ClientOptions, 'apiKey'>;\n}\n\nexport interface OpenAIVoiceConfig {\n  speech?: {\n    model: 'tts-1' | 'tts-1-hd';\n    apiKey?: string;\n    speaker?: OpenAIVoiceId;\n    options?: Omit<ClientOptions, 'apiKey'>;\n  };\n  listening?: {\n    model: 'whisper-1';\n    apiKey?: string;\n    options?: Omit<ClientOptions, 'apiKey'>;\n  };\n}\n\nexport class OpenAIVoice extends MastraVoice {\n  speechClient?: OpenAI;\n  listeningClient?: OpenAI;\n\n  /**\n   * Constructs an instance of OpenAIVoice with optional configurations for speech and listening models.\n   *\n   * @param {Object} [config] - Configuration options for the OpenAIVoice instance.\n   * @param {OpenAIConfig} [config.listeningModel] - Configuration for the listening model, including model name and API key.\n   * @param {OpenAIConfig} [config.speechModel] - Configuration for the speech model, including model name and API key.\n   * @param {string} [config.speaker] - The default speaker's voice to use for speech synthesis.\n   * @throws {Error} - Throws an error if no API key is provided for either the speech or listening model.\n   */\n  constructor({\n    listeningModel,\n    speechModel,\n    speaker,\n  }: {\n    listeningModel?: OpenAIConfig;\n    speechModel?: OpenAIConfig;\n    speaker?: string;\n  } = {}) {\n    const defaultApiKey = process.env.OPENAI_API_KEY;\n    const defaultSpeechModel = {\n      name: 'tts-1',\n      apiKey: defaultApiKey,\n    };\n    const defaultListeningModel = {\n      name: 'whisper-1',\n      apiKey: defaultApiKey,\n    };\n\n    super({\n      speechModel: {\n        name: speechModel?.name ?? defaultSpeechModel.name,\n        apiKey: speechModel?.apiKey ?? defaultSpeechModel.apiKey,\n      },\n      listeningModel: {\n        name: listeningModel?.name ?? defaultListeningModel.name,\n        apiKey: listeningModel?.apiKey ?? defaultListeningModel.apiKey,\n      },\n      speaker: speaker ?? 'alloy',\n    });\n\n    const speechApiKey = speechModel?.apiKey || defaultApiKey;\n    if (!speechApiKey) {\n      throw new Error('No API key provided for speech model');\n    }\n    this.speechClient = new OpenAI({\n      apiKey: speechApiKey,\n      ...speechModel?.options,\n    });\n\n    const listeningApiKey = listeningModel?.apiKey || defaultApiKey;\n    if (!listeningApiKey) {\n      throw new Error('No API key provided for listening model');\n    }\n    this.listeningClient = new OpenAI({\n      apiKey: listeningApiKey,\n      ...listeningModel?.options,\n    });\n\n    if (!this.speechClient && !this.listeningClient) {\n      throw new Error('At least one of OPENAI_API_KEY, speechModel.apiKey, or listeningModel.apiKey must be set');\n    }\n  }\n\n  /**\n   * Retrieves a list of available speakers for the speech model.\n   *\n   * @returns {Promise<Array<{ voiceId: OpenAIVoiceId }>>} - A promise that resolves to an array of objects,\n   * each containing a `voiceId` representing an available speaker.\n   * @throws {Error} - Throws an error if the speech model is not configured.\n   */\n  async getSpeakers(): Promise<Array<{ voiceId: OpenAIVoiceId }>> {\n    if (!this.speechModel) {\n      throw new Error('Speech model not configured');\n    }\n\n    return [\n      { voiceId: 'alloy' },\n      { voiceId: 'echo' },\n      { voiceId: 'fable' },\n      { voiceId: 'onyx' },\n      { voiceId: 'nova' },\n      { voiceId: 'shimmer' },\n      { voiceId: 'ash' },\n      { voiceId: 'coral' },\n      { voiceId: 'sage' },\n    ];\n  }\n\n  /**\n   * Converts text or audio input into speech using the configured speech model.\n   *\n   * @param {string | NodeJS.ReadableStream} input - The text or audio stream to be converted into speech.\n   * @param {Object} [options] - Optional parameters for the speech synthesis.\n   * @param {string} [options.speaker] - The speaker's voice to use for the speech synthesis.\n   * @param {number} [options.speed] - The speed at which the speech should be synthesized.\n   * @returns {Promise<NodeJS.ReadableStream>} - A promise that resolves to a readable stream of the synthesized audio.\n   * @throws {Error} - Throws an error if the speech model is not configured or if the input text is empty.\n   */\n  async speak(\n    input: string | NodeJS.ReadableStream,\n    options?: {\n      speaker?: string;\n      speed?: number;\n      [key: string]: any;\n    },\n  ): Promise<NodeJS.ReadableStream> {\n    if (!this.speechClient) {\n      throw new Error('Speech model not configured');\n    }\n\n    if (typeof input !== 'string') {\n      const chunks: Buffer[] = [];\n      for await (const chunk of input) {\n        if (typeof chunk === 'string') {\n          chunks.push(Buffer.from(chunk));\n        } else {\n          chunks.push(chunk);\n        }\n      }\n      input = Buffer.concat(chunks).toString('utf-8');\n    }\n\n    if (input.trim().length === 0) {\n      throw new Error('Input text is empty');\n    }\n\n    const { speaker, responseFormat, speed, ...otherOptions } = options || {};\n\n    const response = await this.speechClient!.audio.speech.create({\n      model: this.speechModel?.name ?? 'tts-1',\n      voice: (speaker ?? this.speaker) as OpenAIVoiceId,\n      response_format: responseFormat ?? 'mp3',\n      input,\n      speed: speed || 1.0,\n      ...otherOptions,\n    });\n\n    const passThrough = new PassThrough();\n    const buffer = Buffer.from(await response.arrayBuffer());\n    passThrough.end(buffer);\n    return passThrough;\n  }\n\n  /**\n   * Checks if listening capabilities are enabled.\n   *\n   * @returns {Promise<{ enabled: boolean }>}\n   */\n  async getListener() {\n    if (!this.listeningClient) {\n      return { enabled: false };\n    }\n    return { enabled: true };\n  }\n\n  /**\n   * Transcribes audio from a given stream using the configured listening model.\n   *\n   * @param {NodeJS.ReadableStream} audioStream - The audio stream to be transcribed.\n   * @param {Object} [options] - Optional parameters for the transcription.\n   * @param {string} [options.filetype] - The file type of the audio stream.\n   *                                      Supported types include 'mp3', 'mp4', 'mpeg', 'mpga', 'm4a', 'wav', 'webm'.\n   * @returns {Promise<string>} - A promise that resolves to the transcribed text.\n   * @throws {Error} - Throws an error if the listening model is not configured.\n   */\n  async listen(\n    audioStream: NodeJS.ReadableStream,\n    options?: {\n      filetype?: 'mp3' | 'mp4' | 'mpeg' | 'mpga' | 'm4a' | 'wav' | 'webm';\n      [key: string]: any;\n    },\n  ): Promise<string> {\n    if (!this.listeningClient) {\n      throw new Error('Listening model not configured');\n    }\n\n    const chunks: Buffer[] = [];\n    for await (const chunk of audioStream) {\n      if (typeof chunk === 'string') {\n        chunks.push(Buffer.from(chunk));\n      } else {\n        chunks.push(chunk);\n      }\n    }\n    const audioBuffer = Buffer.concat(chunks);\n\n    const { filetype, ...otherOptions } = options || {};\n    const file = new File([audioBuffer], `audio.${filetype || 'mp3'}`);\n\n    const response = await this.listeningClient!.audio.transcriptions.create({\n      model: this.listeningModel?.name || 'whisper-1',\n      file: file as any,\n      ...otherOptions,\n    });\n\n    return response.text;\n  }\n}\n"]}

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/index.ts"],"names":[],"mappings":";;;;;AA6BO,IAAM,WAAA,GAAN,cAA0B,WAAA,CAAY;AAAA,EAC3C,YAAA;AAAA,EACA,eAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAWA,WAAA,CAAY;AAAA,IACV,cAAA;AAAA,IACA,WAAA;AAAA,IACA;AAAA,GACF,GAII,EAAC,EAAG;AACN,IAAA,MAAM,aAAA,GAAgB,QAAQ,GAAA,CAAI,cAAA;AAClC,IAAA,MAAM,kBAAA,GAAqB;AAAA,MACzB,IAAA,EAAM,OAAA;AAAA,MACN,MAAA,EAAQ;AAAA,KACV;AACA,IAAA,MAAM,qBAAA,GAAwB;AAAA,MAC5B,IAAA,EAAM,WAAA;AAAA,MACN,MAAA,EAAQ;AAAA,KACV;AAEA,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,WAAA,EAAa,IAAA,IAAQ,kBAAA,CAAmB,IAAA;AAAA,QAC9C,MAAA,EAAQ,WAAA,EAAa,MAAA,IAAU,kBAAA,CAAmB;AAAA,OACpD;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,cAAA,EAAgB,IAAA,IAAQ,qBAAA,CAAsB,IAAA;AAAA,QACpD,MAAA,EAAQ,cAAA,EAAgB,MAAA,IAAU,qBAAA,CAAsB;AAAA,OAC1D;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,YAAA,GAAe,aAAa,MAAA,IAAU,aAAA;AAC5C,IAAA,IAAI,CAAC,YAAA,EAAc;AACjB,MAAA,MAAM,IAAI,MAAM,sCAAsC,CAAA;AAAA,IACxD;AACA,IAAA,IAAA,CAAK,YAAA,GAAe,IAAI,MAAA,CAAO;AAAA,MAC7B,MAAA,EAAQ,YAAA;AAAA,MACR,GAAG,WAAA,EAAa;AAAA,KACjB,CAAA;AAED,IAAA,MAAM,eAAA,GAAkB,gBAAgB,MAAA,IAAU,aAAA;AAClD,IAAA,IAAI,CAAC,eAAA,EAAiB;AACpB,MAAA,MAAM,IAAI,MAAM,yCAAyC,CAAA;AAAA,IAC3D;AACA,IAAA,IAAA,CAAK,eAAA,GAAkB,IAAI,MAAA,CAAO;AAAA,MAChC,MAAA,EAAQ,eAAA;AAAA,MACR,GAAG,cAAA,EAAgB;AAAA,KACpB,CAAA;AAED,IAAA,IAAI,CAAC,IAAA,CAAK,YAAA,IAAgB,CAAC,KAAK,eAAA,EAAiB;AAC/C,MAAA,MAAM,IAAI,MAAM,0FAA0F,CAAA;AAAA,IAC5G;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,WAAA,GAA0D;AAC9D,IAAA,IAAI,CAAC,KAAK,WAAA,EAAa;AACrB,MAAA,MAAM,IAAI,MAAM,6BAA6B,CAAA;AAAA,IAC/C;AAEA,IAAA,OAAO;AAAA,MACL,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,SAAA,EAAU;AAAA,MACrB,EAAE,SAAS,KAAA,EAAM;AAAA,MACjB,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA;AAAO,KACpB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,KAAA,CACJ,KAAA,EACA,OAAA,EAKgC;AAChC,IAAA,IAAI,CAAC,KAAK,YAAA,EAAc;AACtB,MAAA,MAAM,IAAI,MAAM,6BAA6B,CAAA;AAAA,IAC/C;AAEA,IAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,MAAA,MAAM,SAAmB,EAAC;AAC1B,MAAA,WAAA,MAAiB,SAAS,KAAA,EAAO;AAC/B,QAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,UAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,QAChC,CAAA,MAAO;AACL,UAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,QACnB;AAAA,MACF;AACA,MAAA,KAAA,GAAQ,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA,CAAE,SAAS,OAAO,CAAA;AAAA,IAChD;AAEA,IAAA,IAAI,KAAA,CAAM,IAAA,EAAK,CAAE,MAAA,KAAW,CAAA,EAAG;AAC7B,MAAA,MAAM,IAAI,MAAM,qBAAqB,CAAA;AAAA,IACvC;AAEA,IAAA,MAAM,EAAE,SAAS,cAAA,EAAgB,KAAA,EAAO,GAAG,YAAA,EAAa,GAAI,WAAW,EAAC;AAExE,IAAA,MAAM,WAAW,MAAM,IAAA,CAAK,YAAA,CAAc,KAAA,CAAM,OAAO,MAAA,CAAO;AAAA,MAC5D,KAAA,EAAO,IAAA,CAAK,WAAA,EAAa,IAAA,IAAQ,OAAA;AAAA,MACjC,KAAA,EAAQ,WAAW,IAAA,CAAK,OAAA;AAAA,MACxB,iBAAiB,cAAA,IAAkB,KAAA;AAAA,MACnC,KAAA;AAAA,MACA,OAAO,KAAA,IAAS,CAAA;AAAA,MAChB,GAAG;AAAA,KACJ,CAAA;AAED,IAAA,MAAM,WAAA,GAAc,IAAI,WAAA,EAAY;AACpC,IAAA,MAAM,SAAS,MAAA,CAAO,IAAA,CAAK,MAAM,QAAA,CAAS,aAAa,CAAA;AACvD,IAAA,WAAA,CAAY,IAAI,MAAM,CAAA;AACtB,IAAA,OAAO,WAAA;AAAA,EACT;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAM,WAAA,GAAc;AAClB,IAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AACzB,MAAA,OAAO,EAAE,SAAS,KAAA,EAAM;AAAA,IAC1B;AACA,IAAA,OAAO,EAAE,SAAS,IAAA,EAAK;AAAA,EACzB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,MAAA,CACJ,WAAA,EACA,OAAA,EAIiB;AACjB,IAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AACzB,MAAA,MAAM,IAAI,MAAM,gCAAgC,CAAA;AAAA,IAClD;AAEA,IAAA,MAAM,SAAmB,EAAC;AAC1B,IAAA,WAAA,MAAiB,SAAS,WAAA,EAAa;AACrC,MAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,QAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,MAChC,CAAA,MAAO;AACL,QAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,MACnB;AAAA,IACF;AACA,IAAA,MAAM,WAAA,GAAc,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA;AAExC,IAAA,MAAM,EAAE,QAAA,EAAU,GAAG,YAAA,EAAa,GAAI,WAAW,EAAC;AAClD,IAAA,MAAM,IAAA,GAAO,IAAI,IAAA,CAAK,CAAC,WAAW,CAAA,EAAG,CAAA,MAAA,EAAS,QAAA,IAAY,KAAK,CAAA,CAAE,CAAA;AAEjE,IAAA,MAAM,WAAW,MAAM,IAAA,CAAK,eAAA,CAAiB,KAAA,CAAM,eAAe,MAAA,CAAO;AAAA,MACvE,KAAA,EAAO,IAAA,CAAK,cAAA,EAAgB,IAAA,IAAQ,WAAA;AAAA,MACpC,IAAA;AAAA,MACA,GAAG;AAAA,KACJ,CAAA;AAED,IAAA,OAAO,QAAA,CAAS,IAAA;AAAA,EAClB;AACF","file":"index.js","sourcesContent":["import { PassThrough } from 'stream';\n\nimport { MastraVoice } from '@mastra/core/voice';\nimport OpenAI from 'openai';\nimport type { ClientOptions } from 'openai';\n\ntype OpenAIVoiceId = 'alloy' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer' | 'ash' | 'coral' | 'sage';\ntype OpenAIModel = 'tts-1' | 'tts-1-hd' | 'whisper-1';\n\nexport interface OpenAIConfig {\n  name?: OpenAIModel;\n  apiKey?: string;\n  options?: Omit<ClientOptions, 'apiKey'>;\n}\n\nexport interface OpenAIVoiceConfig {\n  speech?: {\n    model: 'tts-1' | 'tts-1-hd';\n    apiKey?: string;\n    speaker?: OpenAIVoiceId;\n    options?: Omit<ClientOptions, 'apiKey'>;\n  };\n  listening?: {\n    model: 'whisper-1';\n    apiKey?: string;\n    options?: Omit<ClientOptions, 'apiKey'>;\n  };\n}\n\nexport class OpenAIVoice extends MastraVoice {\n  speechClient?: OpenAI;\n  listeningClient?: OpenAI;\n\n  /**\n   * Constructs an instance of OpenAIVoice with optional configurations for speech and listening models.\n   *\n   * @param {Object} [config] - Configuration options for the OpenAIVoice instance.\n   * @param {OpenAIConfig} [config.listeningModel] - Configuration for the listening model, including model name and API key.\n   * @param {OpenAIConfig} [config.speechModel] - Configuration for the speech model, including model name and API key.\n   * @param {string} [config.speaker] - The default speaker's voice to use for speech synthesis.\n   * @throws {Error} - Throws an error if no API key is provided for either the speech or listening model.\n   */\n  constructor({\n    listeningModel,\n    speechModel,\n    speaker,\n  }: {\n    listeningModel?: OpenAIConfig;\n    speechModel?: OpenAIConfig;\n    speaker?: string;\n  } = {}) {\n    const defaultApiKey = process.env.OPENAI_API_KEY;\n    const defaultSpeechModel = {\n      name: 'tts-1',\n      apiKey: defaultApiKey,\n    };\n    const defaultListeningModel = {\n      name: 'whisper-1',\n      apiKey: defaultApiKey,\n    };\n\n    super({\n      speechModel: {\n        name: speechModel?.name ?? defaultSpeechModel.name,\n        apiKey: speechModel?.apiKey ?? defaultSpeechModel.apiKey,\n      },\n      listeningModel: {\n        name: listeningModel?.name ?? defaultListeningModel.name,\n        apiKey: listeningModel?.apiKey ?? defaultListeningModel.apiKey,\n      },\n      speaker: speaker ?? 'alloy',\n    });\n\n    const speechApiKey = speechModel?.apiKey || defaultApiKey;\n    if (!speechApiKey) {\n      throw new Error('No API key provided for speech model');\n    }\n    this.speechClient = new OpenAI({\n      apiKey: speechApiKey,\n      ...speechModel?.options,\n    });\n\n    const listeningApiKey = listeningModel?.apiKey || defaultApiKey;\n    if (!listeningApiKey) {\n      throw new Error('No API key provided for listening model');\n    }\n    this.listeningClient = new OpenAI({\n      apiKey: listeningApiKey,\n      ...listeningModel?.options,\n    });\n\n    if (!this.speechClient && !this.listeningClient) {\n      throw new Error('At least one of OPENAI_API_KEY, speechModel.apiKey, or listeningModel.apiKey must be set');\n    }\n  }\n\n  /**\n   * Retrieves a list of available speakers for the speech model.\n   *\n   * @returns {Promise<Array<{ voiceId: OpenAIVoiceId }>>} - A promise that resolves to an array of objects,\n   * each containing a `voiceId` representing an available speaker.\n   * @throws {Error} - Throws an error if the speech model is not configured.\n   */\n  async getSpeakers(): Promise<Array<{ voiceId: OpenAIVoiceId }>> {\n    if (!this.speechModel) {\n      throw new Error('Speech model not configured');\n    }\n\n    return [\n      { voiceId: 'alloy' },\n      { voiceId: 'echo' },\n      { voiceId: 'fable' },\n      { voiceId: 'onyx' },\n      { voiceId: 'nova' },\n      { voiceId: 'shimmer' },\n      { voiceId: 'ash' },\n      { voiceId: 'coral' },\n      { voiceId: 'sage' },\n    ];\n  }\n\n  /**\n   * Converts text or audio input into speech using the configured speech model.\n   *\n   * @param {string | NodeJS.ReadableStream} input - The text or audio stream to be converted into speech.\n   * @param {Object} [options] - Optional parameters for the speech synthesis.\n   * @param {string} [options.speaker] - The speaker's voice to use for the speech synthesis.\n   * @param {number} [options.speed] - The speed at which the speech should be synthesized.\n   * @returns {Promise<NodeJS.ReadableStream>} - A promise that resolves to a readable stream of the synthesized audio.\n   * @throws {Error} - Throws an error if the speech model is not configured or if the input text is empty.\n   */\n  async speak(\n    input: string | NodeJS.ReadableStream,\n    options?: {\n      speaker?: string;\n      speed?: number;\n      [key: string]: any;\n    },\n  ): Promise<NodeJS.ReadableStream> {\n    if (!this.speechClient) {\n      throw new Error('Speech model not configured');\n    }\n\n    if (typeof input !== 'string') {\n      const chunks: Buffer[] = [];\n      for await (const chunk of input) {\n        if (typeof chunk === 'string') {\n          chunks.push(Buffer.from(chunk));\n        } else {\n          chunks.push(chunk);\n        }\n      }\n      input = Buffer.concat(chunks).toString('utf-8');\n    }\n\n    if (input.trim().length === 0) {\n      throw new Error('Input text is empty');\n    }\n\n    const { speaker, responseFormat, speed, ...otherOptions } = options || {};\n\n    const response = await this.speechClient!.audio.speech.create({\n      model: this.speechModel?.name ?? 'tts-1',\n      voice: (speaker ?? this.speaker) as OpenAIVoiceId,\n      response_format: responseFormat ?? 'mp3',\n      input,\n      speed: speed || 1.0,\n      ...otherOptions,\n    });\n\n    const passThrough = new PassThrough();\n    const buffer = Buffer.from(await response.arrayBuffer());\n    passThrough.end(buffer);\n    return passThrough;\n  }\n\n  /**\n   * Checks if listening capabilities are enabled.\n   *\n   * @returns {Promise<{ enabled: boolean }>}\n   */\n  async getListener() {\n    if (!this.listeningClient) {\n      return { enabled: false };\n    }\n    return { enabled: true };\n  }\n\n  /**\n   * Transcribes audio from a given stream using the configured listening model.\n   *\n   * @param {NodeJS.ReadableStream} audioStream - The audio stream to be transcribed.\n   * @param {Object} [options] - Optional parameters for the transcription.\n   * @param {string} [options.filetype] - The file type of the audio stream.\n   *                                      Supported types include 'mp3', 'mp4', 'mpeg', 'mpga', 'm4a', 'wav', 'webm'.\n   * @returns {Promise<string>} - A promise that resolves to the transcribed text.\n   * @throws {Error} - Throws an error if the listening model is not configured.\n   */\n  async listen(\n    audioStream: NodeJS.ReadableStream,\n    options?: {\n      filetype?: 'mp3' | 'mp4' | 'mpeg' | 'mpga' | 'm4a' | 'wav' | 'webm';\n      [key: string]: any;\n    },\n  ): Promise<string> {\n    if (!this.listeningClient) {\n      throw new Error('Listening model not configured');\n    }\n\n    const chunks: Buffer[] = [];\n    for await (const chunk of audioStream) {\n      if (typeof chunk === 'string') {\n        chunks.push(Buffer.from(chunk));\n      } else {\n        chunks.push(chunk);\n      }\n    }\n    const audioBuffer = Buffer.concat(chunks);\n\n    const { filetype, ...otherOptions } = options || {};\n    const file = new File([audioBuffer], `audio.${filetype || 'mp3'}`);\n\n    const response = await this.listeningClient!.audio.transcriptions.create({\n      model: this.listeningModel?.name || 'whisper-1',\n      file: file as any,\n      ...otherOptions,\n    });\n\n    return response.text;\n  }\n}\n"]}
+{"version":3,"sources":["../src/index.ts"],"names":[],"mappings":";;;;;AA6BO,IAAM,WAAA,GAAN,cAA0B,WAAA,CAAY;AAAA,EAC3C,YAAA;AAAA,EACA,eAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAWA,WAAA,CAAY;AAAA,IACV,cAAA;AAAA,IACA,WAAA;AAAA,IACA;AAAA,GACF,GAII,EAAC,EAAG;AACN,IAAA,MAAM,aAAA,GAAgB,QAAQ,GAAA,CAAI,cAAA;AAClC,IAAA,MAAM,kBAAA,GAAqB;AAAA,MACzB,IAAA,EAAM,OAAA;AAAA,MACN,MAAA,EAAQ;AAAA,KACV;AACA,IAAA,MAAM,qBAAA,GAAwB;AAAA,MAC5B,IAAA,EAAM,WAAA;AAAA,MACN,MAAA,EAAQ;AAAA,KACV;AAEA,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,WAAA,EAAa,IAAA,IAAQ,kBAAA,CAAmB,IAAA;AAAA,QAC9C,MAAA,EAAQ,WAAA,EAAa,MAAA,IAAU,kBAAA,CAAmB;AAAA,OACpD;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,cAAA,EAAgB,IAAA,IAAQ,qBAAA,CAAsB,IAAA;AAAA,QACpD,MAAA,EAAQ,cAAA,EAAgB,MAAA,IAAU,qBAAA,CAAsB;AAAA,OAC1D;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,YAAA,GAAe,aAAa,MAAA,IAAU,aAAA;AAC5C,IAAA,IAAI,CAAC,YAAA,EAAc;AACjB,MAAA,MAAM,IAAI,MAAM,sCAAsC,CAAA;AAAA,IACxD;AACA,IAAA,IAAA,CAAK,YAAA,GAAe,IAAI,MAAA,CAAO;AAAA,MAC7B,MAAA,EAAQ,YAAA;AAAA,MACR,GAAG,WAAA,EAAa;AAAA,KACjB,CAAA;AAED,IAAA,MAAM,eAAA,GAAkB,gBAAgB,MAAA,IAAU,aAAA;AAClD,IAAA,IAAI,CAAC,eAAA,EAAiB;AACpB,MAAA,MAAM,IAAI,MAAM,yCAAyC,CAAA;AAAA,IAC3D;AACA,IAAA,IAAA,CAAK,eAAA,GAAkB,IAAI,MAAA,CAAO;AAAA,MAChC,MAAA,EAAQ,eAAA;AAAA,MACR,GAAG,cAAA,EAAgB;AAAA,KACpB,CAAA;AAED,IAAA,IAAI,CAAC,IAAA,CAAK,YAAA,IAAgB,CAAC,KAAK,eAAA,EAAiB;AAC/C,MAAA,MAAM,IAAI,MAAM,0FAA0F,CAAA;AAAA,IAC5G;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,WAAA,GAA0D;AAC9D,IAAA,IAAI,CAAC,KAAK,WAAA,EAAa;AACrB,MAAA,MAAM,IAAI,MAAM,6BAA6B,CAAA;AAAA,IAC/C;AAEA,IAAA,OAAO;AAAA,MACL,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,MAAA,EAAO;AAAA,MAClB,EAAE,SAAS,SAAA,EAAU;AAAA,MACrB,EAAE,SAAS,KAAA,EAAM;AAAA,MACjB,EAAE,SAAS,OAAA,EAAQ;AAAA,MACnB,EAAE,SAAS,MAAA;AAAO,KACpB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,KAAA,CACJ,KAAA,EACA,OAAA,EAKgC;AAChC,IAAA,IAAI,CAAC,KAAK,YAAA,EAAc;AACtB,MAAA,MAAM,IAAI,MAAM,6BAA6B,CAAA;AAAA,IAC/C;AAEA,IAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,MAAA,MAAM,SAAmB,EAAC;AAC1B,MAAA,WAAA,MAAiB,SAAS,KAAA,EAAO;AAC/B,QAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,UAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,QAChC,CAAA,MAAO;AACL,UAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,QACnB;AAAA,MACF;AACA,MAAA,KAAA,GAAQ,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA,CAAE,SAAS,OAAO,CAAA;AAAA,IAChD;AAEA,IAAA,IAAI,KAAA,CAAM,IAAA,EAAK,CAAE,MAAA,KAAW,CAAA,EAAG;AAC7B,MAAA,MAAM,IAAI,MAAM,qBAAqB,CAAA;AAAA,IACvC;AAEA,IAAA,MAAM,EAAE,SAAS,cAAA,EAAgB,KAAA,EAAO,GAAG,YAAA,EAAa,GAAI,WAAW,EAAC;AAExE,IAAA,MAAM,WAAW,MAAM,IAAA,CAAK,YAAA,CAAc,KAAA,CAAM,OAAO,MAAA,CAAO;AAAA,MAC5D,KAAA,EAAO,IAAA,CAAK,WAAA,EAAa,IAAA,IAAQ,OAAA;AAAA,MACjC,KAAA,EAAQ,WAAW,IAAA,CAAK,OAAA;AAAA,MACxB,iBAAiB,cAAA,IAAkB,KAAA;AAAA,MACnC,KAAA;AAAA,MACA,OAAO,KAAA,IAAS,CAAA;AAAA,MAChB,GAAG;AAAA,KACJ,CAAA;AAED,IAAA,MAAM,WAAA,GAAc,IAAI,WAAA,EAAY;AACpC,IAAA,MAAM,SAAS,MAAA,CAAO,IAAA,CAAK,MAAM,QAAA,CAAS,aAAa,CAAA;AACvD,IAAA,WAAA,CAAY,IAAI,MAAM,CAAA;AACtB,IAAA,OAAO,WAAA;AAAA,EACT;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAM,WAAA,GAAc;AAClB,IAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AACzB,MAAA,OAAO,EAAE,SAAS,KAAA,EAAM;AAAA,IAC1B;AACA,IAAA,OAAO,EAAE,SAAS,IAAA,EAAK;AAAA,EACzB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYA,MAAM,MAAA,CACJ,WAAA,EACA,OAAA,EAIiB;AACjB,IAAA,IAAI,CAAC,KAAK,eAAA,EAAiB;AACzB,MAAA,MAAM,IAAI,MAAM,gCAAgC,CAAA;AAAA,IAClD;AAEA,IAAA,MAAM,SAAmB,EAAC;AAC1B,IAAA,WAAA,MAAiB,SAAS,WAAA,EAAa;AACrC,MAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,QAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,MAChC,CAAA,MAAO;AACL,QAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,MACnB;AAAA,IACF;AACA,IAAA,MAAM,WAAA,GAAc,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA;AAExC,IAAA,MAAM,EAAE,QAAA,EAAU,GAAG,YAAA,EAAa,GAAI,WAAW,EAAC;AAClD,IAAA,MAAM,IAAA,GAAO,IAAI,IAAA,CAAK,CAAC,WAAW,CAAA,EAAG,CAAA,MAAA,EAAS,QAAA,IAAY,KAAK,CAAA,CAAE,CAAA;AAEjE,IAAA,MAAM,WAAW,MAAM,IAAA,CAAK,eAAA,CAAiB,KAAA,CAAM,eAAe,MAAA,CAAO;AAAA,MACvE,KAAA,EAAO,IAAA,CAAK,cAAA,EAAgB,IAAA,IAAQ,WAAA;AAAA,MACpC,IAAA;AAAA,MACA,GAAG;AAAA,KACJ,CAAA;AAED,IAAA,OAAO,QAAA,CAAS,IAAA;AAAA,EAClB;AACF","file":"index.js","sourcesContent":["import { PassThrough } from 'node:stream';\n\nimport { MastraVoice } from '@mastra/core/voice';\nimport OpenAI from 'openai';\nimport type { ClientOptions } from 'openai';\n\ntype OpenAIVoiceId = 'alloy' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer' | 'ash' | 'coral' | 'sage';\ntype OpenAIModel = 'tts-1' | 'tts-1-hd' | 'whisper-1';\n\nexport interface OpenAIConfig {\n  name?: OpenAIModel;\n  apiKey?: string;\n  options?: Omit<ClientOptions, 'apiKey'>;\n}\n\nexport interface OpenAIVoiceConfig {\n  speech?: {\n    model: 'tts-1' | 'tts-1-hd';\n    apiKey?: string;\n    speaker?: OpenAIVoiceId;\n    options?: Omit<ClientOptions, 'apiKey'>;\n  };\n  listening?: {\n    model: 'whisper-1';\n    apiKey?: string;\n    options?: Omit<ClientOptions, 'apiKey'>;\n  };\n}\n\nexport class OpenAIVoice extends MastraVoice {\n  speechClient?: OpenAI;\n  listeningClient?: OpenAI;\n\n  /**\n   * Constructs an instance of OpenAIVoice with optional configurations for speech and listening models.\n   *\n   * @param {Object} [config] - Configuration options for the OpenAIVoice instance.\n   * @param {OpenAIConfig} [config.listeningModel] - Configuration for the listening model, including model name and API key.\n   * @param {OpenAIConfig} [config.speechModel] - Configuration for the speech model, including model name and API key.\n   * @param {string} [config.speaker] - The default speaker's voice to use for speech synthesis.\n   * @throws {Error} - Throws an error if no API key is provided for either the speech or listening model.\n   */\n  constructor({\n    listeningModel,\n    speechModel,\n    speaker,\n  }: {\n    listeningModel?: OpenAIConfig;\n    speechModel?: OpenAIConfig;\n    speaker?: string;\n  } = {}) {\n    const defaultApiKey = process.env.OPENAI_API_KEY;\n    const defaultSpeechModel = {\n      name: 'tts-1',\n      apiKey: defaultApiKey,\n    };\n    const defaultListeningModel = {\n      name: 'whisper-1',\n      apiKey: defaultApiKey,\n    };\n\n    super({\n      speechModel: {\n        name: speechModel?.name ?? defaultSpeechModel.name,\n        apiKey: speechModel?.apiKey ?? defaultSpeechModel.apiKey,\n      },\n      listeningModel: {\n        name: listeningModel?.name ?? defaultListeningModel.name,\n        apiKey: listeningModel?.apiKey ?? defaultListeningModel.apiKey,\n      },\n      speaker: speaker ?? 'alloy',\n    });\n\n    const speechApiKey = speechModel?.apiKey || defaultApiKey;\n    if (!speechApiKey) {\n      throw new Error('No API key provided for speech model');\n    }\n    this.speechClient = new OpenAI({\n      apiKey: speechApiKey,\n      ...speechModel?.options,\n    });\n\n    const listeningApiKey = listeningModel?.apiKey || defaultApiKey;\n    if (!listeningApiKey) {\n      throw new Error('No API key provided for listening model');\n    }\n    this.listeningClient = new OpenAI({\n      apiKey: listeningApiKey,\n      ...listeningModel?.options,\n    });\n\n    if (!this.speechClient && !this.listeningClient) {\n      throw new Error('At least one of OPENAI_API_KEY, speechModel.apiKey, or listeningModel.apiKey must be set');\n    }\n  }\n\n  /**\n   * Retrieves a list of available speakers for the speech model.\n   *\n   * @returns {Promise<Array<{ voiceId: OpenAIVoiceId }>>} - A promise that resolves to an array of objects,\n   * each containing a `voiceId` representing an available speaker.\n   * @throws {Error} - Throws an error if the speech model is not configured.\n   */\n  async getSpeakers(): Promise<Array<{ voiceId: OpenAIVoiceId }>> {\n    if (!this.speechModel) {\n      throw new Error('Speech model not configured');\n    }\n\n    return [\n      { voiceId: 'alloy' },\n      { voiceId: 'echo' },\n      { voiceId: 'fable' },\n      { voiceId: 'onyx' },\n      { voiceId: 'nova' },\n      { voiceId: 'shimmer' },\n      { voiceId: 'ash' },\n      { voiceId: 'coral' },\n      { voiceId: 'sage' },\n    ];\n  }\n\n  /**\n   * Converts text or audio input into speech using the configured speech model.\n   *\n   * @param {string | NodeJS.ReadableStream} input - The text or audio stream to be converted into speech.\n   * @param {Object} [options] - Optional parameters for the speech synthesis.\n   * @param {string} [options.speaker] - The speaker's voice to use for the speech synthesis.\n   * @param {number} [options.speed] - The speed at which the speech should be synthesized.\n   * @returns {Promise<NodeJS.ReadableStream>} - A promise that resolves to a readable stream of the synthesized audio.\n   * @throws {Error} - Throws an error if the speech model is not configured or if the input text is empty.\n   */\n  async speak(\n    input: string | NodeJS.ReadableStream,\n    options?: {\n      speaker?: string;\n      speed?: number;\n      [key: string]: any;\n    },\n  ): Promise<NodeJS.ReadableStream> {\n    if (!this.speechClient) {\n      throw new Error('Speech model not configured');\n    }\n\n    if (typeof input !== 'string') {\n      const chunks: Buffer[] = [];\n      for await (const chunk of input) {\n        if (typeof chunk === 'string') {\n          chunks.push(Buffer.from(chunk));\n        } else {\n          chunks.push(chunk);\n        }\n      }\n      input = Buffer.concat(chunks).toString('utf-8');\n    }\n\n    if (input.trim().length === 0) {\n      throw new Error('Input text is empty');\n    }\n\n    const { speaker, responseFormat, speed, ...otherOptions } = options || {};\n\n    const response = await this.speechClient!.audio.speech.create({\n      model: this.speechModel?.name ?? 'tts-1',\n      voice: (speaker ?? this.speaker) as OpenAIVoiceId,\n      response_format: responseFormat ?? 'mp3',\n      input,\n      speed: speed || 1.0,\n      ...otherOptions,\n    });\n\n    const passThrough = new PassThrough();\n    const buffer = Buffer.from(await response.arrayBuffer());\n    passThrough.end(buffer);\n    return passThrough;\n  }\n\n  /**\n   * Checks if listening capabilities are enabled.\n   *\n   * @returns {Promise<{ enabled: boolean }>}\n   */\n  async getListener() {\n    if (!this.listeningClient) {\n      return { enabled: false };\n    }\n    return { enabled: true };\n  }\n\n  /**\n   * Transcribes audio from a given stream using the configured listening model.\n   *\n   * @param {NodeJS.ReadableStream} audioStream - The audio stream to be transcribed.\n   * @param {Object} [options] - Optional parameters for the transcription.\n   * @param {string} [options.filetype] - The file type of the audio stream.\n   *                                      Supported types include 'mp3', 'mp4', 'mpeg', 'mpga', 'm4a', 'wav', 'webm'.\n   * @returns {Promise<string>} - A promise that resolves to the transcribed text.\n   * @throws {Error} - Throws an error if the listening model is not configured.\n   */\n  async listen(\n    audioStream: NodeJS.ReadableStream,\n    options?: {\n      filetype?: 'mp3' | 'mp4' | 'mpeg' | 'mpga' | 'm4a' | 'wav' | 'webm';\n      [key: string]: any;\n    },\n  ): Promise<string> {\n    if (!this.listeningClient) {\n      throw new Error('Listening model not configured');\n    }\n\n    const chunks: Buffer[] = [];\n    for await (const chunk of audioStream) {\n      if (typeof chunk === 'string') {\n        chunks.push(Buffer.from(chunk));\n      } else {\n        chunks.push(chunk);\n      }\n    }\n    const audioBuffer = Buffer.concat(chunks);\n\n    const { filetype, ...otherOptions } = options || {};\n    const file = new File([audioBuffer], `audio.${filetype || 'mp3'}`);\n\n    const response = await this.listeningClient!.audio.transcriptions.create({\n      model: this.listeningModel?.name || 'whisper-1',\n      file: file as any,\n      ...otherOptions,\n    });\n\n    return response.text;\n  }\n}\n"]}